Graph Convolution Networks for Probabilistic Modeling of Driving Acceleration
This work addresses acceleration prediction for autonomous pilots and driver-assistance systems, representing an incremental improvement through hybrid methods.
The paper tackled the problem of predicting vehicle acceleration for autonomous driving by proposing Graph Convolution Networks to model spatial relationships and integrating Recurrent Neural Networks for temporal complexity, resulting in outperforming state-of-the-art methods in generating realistic trajectories over a prediction horizon.
The ability to model and predict ego-vehicle's surrounding traffic is crucial for autonomous pilots and intelligent driver-assistance systems. Acceleration prediction is important as one of the major components of traffic prediction. This paper proposes novel approaches to the acceleration prediction problem. By representing spatial relationships between vehicles with a graph model, we build a generalized acceleration prediction framework. This paper studies the effectiveness of proposed Graph Convolution Networks, which operate on graphs predicting the acceleration distribution for vehicles driving on highways. We further investigate prediction improvement through integrating of Recurrent Neural Networks to disentangle the temporal complexity inherent in the traffic data. Results from simulation studies using comprehensive performance metrics support the conclusion that our proposed networks outperform state-of-the-art methods in generating realistic trajectories over a prediction horizon.